Stochastic systems are systems in which changes are random. In which the predicted values depend on a probability distribution. An example of a stochastic system in a power system, the operation of which is affected by many random factors, their analysis and control will allow you to control the safe cycle and reliability of operation. Currently, there are methods and mathematical tools that allow us to estimate the likelihood of any phenomenon and situation with acceptable accuracy, however, they are practically not used to solve this problem on electrified railway transport. Therefore, the work summarizes the existing methods of probabilistic forecasting, and gives recommendations on their application to solve the existing problematic of the issue. Further, the paper shows a method for determining the probability of failure of a constituent structural element of any, arbitrarily complex, stochastic system, to which the contact network of electrified railways belongs. In the conclusion of the work, an elementary method-oriented software tool with the functional purpose of automating statistical methods for solving problems of primary data processing and calculating elementary statistics in the process of risk management is proposed, as well as loading and maintaining a database that is subsequently oriented to the principles of machine learning.

Keywords: electrified railways, stochastic systems, operational reliability, probability of failure, forecasting